Home icon

DeepSeek-V4-Pro, DeepSeek-V4-Flash, and DeepSeek-V4.1-Flash models now available on Amazon SageMaker JumpStart

News



This article announces the availability of three DeepSeek foundation models on Amazon SageMaker JumpStart, expanding AWS customers' access to open-weight Mixture-of-Experts language models.

  • DeepSeek-V4-Pro: 1.6T-parameter model with 1M-token context for complex reasoning and high-quality text generation
  • DeepSeek-V4-Flash: 284B-parameter model activating 13B parameters per token for cost-efficient production deployments
  • DeepSeek-V4.1-Flash: 552B-parameter model with native multimodal support and 1/4 KV cache footprint for agentic workloads
  • All models released under MIT license with frontier-class performance across reasoning, coding, and agentic tasks
  • Deploy models with a few clicks via SageMaker JumpStart console or Python SDK

These models enable AWS customers to leverage efficient frontier-class AI capabilities for diverse use cases with reduced computational overhead.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Jan 31
2025
DeepSeek-R1 model now available in Amazon Bedrock Marketplace and Amazon SageMaker JumpStart
Nov 12
2026
Ornith-1.0-9B and Ornith-1.0-35B models now available on Amazon SageMaker JumpStart
Feb 2
2026
DeepSeek OCR, MiniMax M2.1, and Qwen3-VL-8B-Instruct models are now available on SageMaker JumpStart
Jan 31
2025
DeepSeek-R1 models now available on AWS

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.